← Latest products

Ratel

give agents unlimited tools and skills without context bloat. Context engineering for AI agents. ~80% fewer tokens. Fix tool overload. Skills and memory with in-process BM25 and semantic retrieval. Progressive Disclosure. No vector DB. We're Giacomo and Roberto, authors of Ratel ( https://github.com/ratel-ai/ratel ) We used to help SaaS companies build agents on top of their products.

Open source

545 stars · GitHubexternal site

Visit github.comexternal site

Reactions (1)

Similar products

by description similarity

  1. Open-source implementation of Stanford's self-learning agent framework

    github.com

    🧠 Make your agents learn from experience. Now available as a hosted solution at kayba.ai

    Hacker News10 pts

  2. A context aware backend for AI coding agents

    insforge.dev

    Model gateway, compute, deployment, database, auth, and more. Every service built for AI coding agents to operate end to end through CLI and skills.

    Hacker News15 pts

  3. ContextVault

    contextvault.dev

    Shared memory layer for your AI and your team

    Hacker News12 pts

  4. MyScaleDB open-sourced

    github.com

    a SQL vector database to Build AI APPs with SQL

    Hacker News12 pts

  5. StyleSeed

    github.com

    a design-rules engine so AI agents stop building generic UI

    Hacker News24 pts